Accelerated design of photovoltaic Ruddlesden–Popper perovskite Ca6Sn4S14−xOx using machine learning

Ruddlesden–Popper (R–P) phase layered chalcogenide perovskites had attracted broad interest as potential lead-free high-performance photovoltaic absorbers. Ca3Sn2S7 is a graphene-like RP phase perovskite with a ultrahigh carrier mobility and a more significant absorption coefficient in the visible light region than those of the classic hybrid halide perovskite MAPbI3. However, the ultra-low direct bandgap of Ca3Sn2S7 is unfavorable for the photovoltaic application. In this work, we addressed these issues by designing an anion-mixed RP phase perovskite with an appropriate direct bandgap. The idea was to adjust its bandgap with different O proportions from 7.14% to 35.71%. We considered more than 3000 derivative structures of Ca6Sn4S14−xOx (x = 1–5) that were related to the arrangement of mixed S/O atoms. To ensure that the computational models were based on the screened optimal structures, we found that Ca6Sn4S14−xOx (x = 4 and 5) could increase the bandgap of Ca3Sn2S7 into the range of 1.19 eV–1.64 eV and 1.02 eV–1.47 eV, respectively. Meanwhile, Ca6Sn4S14−xOx also had absorption coefficients beyond 105 cm−1. These results made them possible candidates as new-generation photovoltaic absorbers. We also trained the supervised graph convolutional network and the unsupervised Mat-generative adversarial networks (GAN) for accelerating the density functional theory (DFT) calculation of over 3000 structures. Even if considering the time to generate the training samples by DFT, we prove that the Mat-GAN strategy could reduce the DFT calculation consumption by more than 99%. In order to reveal the distributive characteristics of the arrangement of mixed S/O, we adopted active machine learning to analyze the differences of these structures. We found that the O atom would preferentially replace the S in the Sn–S–Sn position.